Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4092 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.5472. Min Act: -0.0002

Data Index: 997127 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4724. Min Act: -0.0002

Data Index: 829147 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3996. Min Act: -0.0002

Data Index: 1336785 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4382. Min Act: -0.0002

Data Index: 988226 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4548. Min Act: -0.0002

Data Index: 193298 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3607. Min Act: -0.0002

Data Index: 441191 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3635. Min Act: -0.0002

Data Index: 1061407 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3676. Min Act: -0.0002

Data Index: 966600 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3877. Min Act: -0.0002

Data Index: 1313651 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3863. Min Act: -0.0002

Data Index: 435161 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3411. Min Act: -0.0002

Data Index: 1239313 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3291. Min Act: -0.0002

Data Index: 1354086 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3286. Min Act: -0.0002

Data Index: 310514 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3803. Min Act: -0.0002

Data Index: 67601 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3460. Min Act: -0.0002

Data Index: 98353 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2865. Min Act: -0.0002

Data Index: 723275 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2838. Min Act: -0.0002

Data Index: 952325 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3036. Min Act: -0.0002

Data Index: 553706 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3149. Min Act: -0.0002

Data Index: 784388 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3166. Min Act: -0.0002

Data Index: 585659 (C4 (Web Text))

Max Activating Token Index: 556